MCP.Market

Lacuna Music MCP server

online · 100% uptime
by JOYLINK-LTD·io.github.JOYLINK-LTD/lacuna-mcp·v0.3.4·4 stars
No reviews yet

Generate AI music via the Lacuna Music API from MCP clients like Claude Desktop & Code.

B82/100grade B
Write a reviewRun it
What users say
No reviews yet
Be the first
Safety scan
B82/100

full report

Adoption
Growing

4 stars

Reviews

Write one

Nobody has reviewed Lacuna Music yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Lacuna Music tools (3, 1 write)

write = sends, deletes, buys or posts
  • generate_musicwrite actionFree

    Create an AI music generation task on Lacuna. Returns immediately with a `pending` task; poll `get_generation` to retrieve the finished tracks and their audio URLs.

  • get_generationFree

    Retrieve the current state of a music generation task by id. Status is `pending`, `ready`, or `failed`; audio URLs appear on `ready`.

  • list_modelsFree

    List the music models available through the API, with their credit cost per task, tracks produced per task, and language coverage.

Public scan report

scanner v0.1.9 · 2026-09-23 · same rubric, same numbers if you re-run it

1 high
  • Code scan2 source files scanned25/25
  • Live reliabilityremote reachable in 943ms20/20
  • Tool poisoning3 tool descriptions checked15/15
  • Auth qualityopen endpoint exposes 1 write-action tools with no auth3/15
  • Maintenancelast push 45 days ago12/15
  • Maintainer identityregistry namespace matches repository owner7/10

Findings (1)

  • highWrite-action tools reachable without authenticationauth.open-write
Overall 82/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Lacuna Music compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
82/100
higher than 63% of 48,255 servers
Tools
3
the typical server has 7
Tools that change things
33%
typical: 0%. Fewer write tools means less an agent can break
Uptime
100%
of our recent checks; the typical remote server answers 100%
Response time
178 ms
faster than 68% of 30,031 servers
GitHub stars
4
more than 82% of 28,688 servers

What its tools let an agent do: 2 read · 1 create

Install Lacuna Music in Claude Code, Cursor or VS Code

claude mcp add --transport http lacuna-mcp https://www.lacuna.fm/mcp
Add to Cursor

What the publisher says

From the Lacuna Music repository's README, as published. We do not edit it. Read it on GitHub

Lacuna developer tools

Open-source SDK, CLI, MCP server, and Agent Skill for the Lacuna Music API. Generate AI music programmatically from any Node 18+ runtime, your shell, an MCP-compatible client, or an AI coding agent that supports the Agent Skills standard.

The three npm packages are released together and share the same API surface. The skill is markdown-only and tracks the latest published packages.

Repository layout

.
├── packages/
│   ├── sdk/                   →  npm: lacuna-sdk
│   ├── cli/                   →  npm: lacuna-toolkit
│   └── mcp/                   →  npm: lacuna-mcp
├── skills/
│   └── lacuna-music/SKILL.md  →  Agent Skill (skills.sh, skillsmp.com, etc.)
├── pnpm-workspace.yaml
├── tsconfig.base.json
└── package.json

This is a pnpm workspace. The CLI and MCP server depend on the SDK via workspace:*, which is rewritten to a real version range on publish. The skill is plain markdown and is not part of the workspace.

Development

pnpm install            # install all workspace deps
pnpm -r run build       # build every package
pnpm -r run typecheck   # typecheck every package
pnpm --filter lacuna-mcp run dev  # iterate on a single package

The SDK must be built before pnpm -r run typecheck can resolve the CLI/MCP packages' types. pnpm -r run build handles dependency order automatically.

Releasing

Each package versions independently from packages//package.json. Bump versions in lockstep, build, then publish:

# bump the version in all three package.jsons + packages/mcp/server.json
# (packages/sdk/src/version.ts is injected from package.json at build time — do not hand-edit)
pnpm -r run build
pnpm --filter lacuna-sdk publish --access public
pnpm --filter lacuna-toolkit publish --access public
pnpm --filter lacuna-mcp publish --access public

workspace:* references in dependencies are rewritten to the published version automatically (pnpm handles this).

Distributing the skill

The skill at skills/lacuna-music/ follows the Agent Skills open standard, so it works with Claude Code, Codex CLI, Cursor, and any other tool that loads SKILL.md files.

There is no submission step for skill marketplaces — they index public GitHub repos automatically:

  • skills.sh (Vercel Labs) ranks skills by anonymous install telemetry. Once the repo is public, anyone can install with npx skills add JOYLINK-LTD/lacuna-toolkit, and installs feed the leaderboard. The CLI auto-discovers SKILL.md files under skills//.
  • skillsmp.com and claudeskills.info crawl public GitHub repos that contain SKILL.md and a minimum of 2 stars.
  • The official anthropics/skills repo accepts community-contributed skills via PR if you want a canonical listing.

To verify discovery locally:

npx skills add JOYLINK-LTD/lacuna-toolkit

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Lacuna Music: common questions

Is Lacuna Music MCP server safe?
Mostly: it is graded B (82/100). Read the Lacuna Music safety report
How do I install Lacuna Music?
It runs remotely at www.lacuna.fm. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Lacuna Music need an API key?
Yes. The registry entry asks for LACUNA_API_KEY.
Is Lacuna Music maintained?
The last commit was 86 days ago (2026-08-10). The latest release is v0.3.4.
Is Lacuna Music up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
How does Lacuna Music compare with other MCP servers?
safety score 82/100 (higher than 63% of 48,255 servers); tools 3 (the typical server has 7); tools that change things 33% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.